© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 71
    Prev
    Next
    INDEX
    Explanations

    airport codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    玩笑
    1.71
    เช่น
    1.67
    В
    1.48
    а
    1.43
    akuwa
    1.43
    揮
    1.41
    透露
    1.41
     adap
    1.40
     laterales
    1.40
    खिल
    1.39
    POSITIVE LOGITS
     QText
    1.88
    ޢ
    1.86
    ιστή
    1.80
     ब्रेस्ट
    1.78
    ισμό
    1.75
    knopf
    1.75
     {,
    1.72
    éal
    1.71
     Affirm
    1.70
    PluginResult
    1.70
    Activations Density 0.000%

    No Known Activations